Commit 02c72d5e authored by David S. Miller's avatar David S. Miller

Merge branch 'virtio-support-packed-ring'

Tiwei Bie says:

====================
virtio: support packed ring

This patch set implements packed ring support in virtio driver.

A performance test between pktgen (pktgen_sample03_burst_single_flow.sh)
and DPDK vhost (testpmd/rxonly/vhost-PMD) has been done, I saw
~30% performance gain in packed ring in this case.

To make this patch set work with below patch set for vhost,
some hacks are needed to set the _F_NEXT flag in indirect
descriptors (this should be fixed in vhost):

https://lkml.org/lkml/2018/7/3/33

v2 -> v3:
- Use leXX instead of virtioXX (MST);
- Refactor split ring first (MST);
- Add debug helpers (MST);
- Put split/packed ring specific fields in sub structures (MST);
- Handle normal descriptors and indirect descriptors differently (MST);
- Track the DMA addr/len related info in a separate structure (MST);
- Calculate AVAIL/USED flags only when wrap counter wraps (MST);
- Define a struct/union to read event structure (MST);
- Define a macro for wrap counter bit in uapi (MST);
- Define the AVAIL/USED bits as shifts instead of values (MST);
- s/_F_/_FLAG_/ in VRING_PACKED_EVENT_* as they are values (MST);
- Drop the notify workaround for QEMU's tx-timer in packed ring (MST);

v1 -> v2:
- Use READ_ONCE() to read event off_wrap and flags together (Jason);
- Add comments related to ccw (Jason);

RFC v6 -> v1:
- Avoid extra virtio_wmb() in virtqueue_enable_cb_delayed_packed()
  when event idx is off (Jason);
- Fix bufs calculation in virtqueue_enable_cb_delayed_packed() (Jason);
- Test the state of the desc at used_idx instead of last_used_idx
  in virtqueue_enable_cb_delayed_packed() (Jason);
- Save wrap counter (as part of queue state) in the return value
  of virtqueue_enable_cb_prepare_packed();
- Refine the packed ring definitions in uapi;
- Rebase on the net-next tree;

RFC v5 -> RFC v6:
- Avoid tracking addr/len/flags when DMA API isn't used (MST/Jason);
- Define wrap counter as bool (Jason);
- Use ALIGN() in vring_init_packed() (Jason);
- Avoid using pointer to track `next` in detach_buf_packed() (Jason);
- Add comments for barriers (Jason);
- Don't enable RING_PACKED on ccw for now (noticed by Jason);
- Refine the memory barrier in virtqueue_poll();
- Add a missing memory barrier in virtqueue_enable_cb_delayed_packed();
- Remove the hacks in virtqueue_enable_cb_prepare_packed();

RFC v4 -> RFC v5:
- Save DMA addr, etc in desc state (Jason);
- Track used wrap counter;

RFC v3 -> RFC v4:
- Make ID allocation support out-of-order (Jason);
- Various fixes for EVENT_IDX support;

RFC v2 -> RFC v3:
- Split into small patches (Jason);
- Add helper virtqueue_use_indirect() (Jason);
- Just set id for the last descriptor of a list (Jason);
- Calculate the prev in virtqueue_add_packed() (Jason);
- Fix/improve desc suppression code (Jason/MST);
- Refine the code layout for XXX_split/packed and wrappers (MST);
- Fix the comments and API in uapi (MST);
- Remove the BUG_ON() for indirect (Jason);
- Some other refinements and bug fixes;

RFC v1 -> RFC v2:
- Add indirect descriptor support - compile test only;
- Add event suppression supprt - compile test only;
- Move vring_packed_init() out of uapi (Jason, MST);
- Merge two loops into one in virtqueue_add_packed() (Jason);
- Split vring_unmap_one() for packed ring and split ring (Jason);
- Avoid using '%' operator (Jason);
- Rename free_head -> next_avail_idx (Jason);
- Add comments for virtio_wmb() in virtqueue_add_packed() (Jason);
- Some other refinements and bug fixes;
====================
Acked-by: default avatarMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 4afe60a9 f959a128
...@@ -129,6 +129,16 @@ static u64 vop_get_features(struct virtio_device *vdev) ...@@ -129,6 +129,16 @@ static u64 vop_get_features(struct virtio_device *vdev)
return features; return features;
} }
static void vop_transport_features(struct virtio_device *vdev)
{
/*
* Packed ring isn't enabled on virtio_vop for now,
* because virtio_vop uses vring_new_virtqueue() which
* creates virtio rings on preallocated memory.
*/
__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
}
static int vop_finalize_features(struct virtio_device *vdev) static int vop_finalize_features(struct virtio_device *vdev)
{ {
unsigned int i, bits; unsigned int i, bits;
...@@ -141,6 +151,9 @@ static int vop_finalize_features(struct virtio_device *vdev) ...@@ -141,6 +151,9 @@ static int vop_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features. */ /* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev); vring_transport_features(vdev);
/* Give virtio_vop a chance to accept features. */
vop_transport_features(vdev);
memset_io(out_features, 0, feature_len); memset_io(out_features, 0, feature_len);
bits = min_t(unsigned, feature_len, bits = min_t(unsigned, feature_len,
sizeof(vdev->features)) * 8; sizeof(vdev->features)) * 8;
......
...@@ -214,6 +214,16 @@ static u64 rproc_virtio_get_features(struct virtio_device *vdev) ...@@ -214,6 +214,16 @@ static u64 rproc_virtio_get_features(struct virtio_device *vdev)
return rsc->dfeatures; return rsc->dfeatures;
} }
static void rproc_transport_features(struct virtio_device *vdev)
{
/*
* Packed ring isn't enabled on remoteproc for now,
* because remoteproc uses vring_new_virtqueue() which
* creates virtio rings on preallocated memory.
*/
__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
}
static int rproc_virtio_finalize_features(struct virtio_device *vdev) static int rproc_virtio_finalize_features(struct virtio_device *vdev)
{ {
struct rproc_vdev *rvdev = vdev_to_rvdev(vdev); struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
...@@ -224,6 +234,9 @@ static int rproc_virtio_finalize_features(struct virtio_device *vdev) ...@@ -224,6 +234,9 @@ static int rproc_virtio_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features */ /* Give virtio_ring a chance to accept features */
vring_transport_features(vdev); vring_transport_features(vdev);
/* Give virtio_rproc a chance to accept features. */
rproc_transport_features(vdev);
/* Make sure we don't have any features > 32 bits! */ /* Make sure we don't have any features > 32 bits! */
BUG_ON((u32)vdev->features != vdev->features); BUG_ON((u32)vdev->features != vdev->features);
......
...@@ -765,6 +765,17 @@ static u64 virtio_ccw_get_features(struct virtio_device *vdev) ...@@ -765,6 +765,17 @@ static u64 virtio_ccw_get_features(struct virtio_device *vdev)
return rc; return rc;
} }
static void ccw_transport_features(struct virtio_device *vdev)
{
/*
* Packed ring isn't enabled on virtio_ccw for now,
* because virtio_ccw uses some legacy accessors,
* e.g. virtqueue_get_avail() and virtqueue_get_used()
* which aren't available in packed ring currently.
*/
__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
}
static int virtio_ccw_finalize_features(struct virtio_device *vdev) static int virtio_ccw_finalize_features(struct virtio_device *vdev)
{ {
struct virtio_ccw_device *vcdev = to_vc_device(vdev); struct virtio_ccw_device *vcdev = to_vc_device(vdev);
...@@ -791,6 +802,9 @@ static int virtio_ccw_finalize_features(struct virtio_device *vdev) ...@@ -791,6 +802,9 @@ static int virtio_ccw_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features. */ /* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev); vring_transport_features(vdev);
/* Give virtio_ccw a chance to accept features. */
ccw_transport_features(vdev);
features->index = 0; features->index = 0;
features->features = cpu_to_le32((u32)vdev->features); features->features = cpu_to_le32((u32)vdev->features);
/* Write the first half of the feature bits to the host. */ /* Write the first half of the feature bits to the host. */
......
This diff is collapsed.
...@@ -75,6 +75,9 @@ ...@@ -75,6 +75,9 @@
*/ */
#define VIRTIO_F_IOMMU_PLATFORM 33 #define VIRTIO_F_IOMMU_PLATFORM 33
/* This feature indicates support for the packed virtqueue layout. */
#define VIRTIO_F_RING_PACKED 34
/* /*
* Does the device support Single Root I/O Virtualization? * Does the device support Single Root I/O Virtualization?
*/ */
......
...@@ -44,6 +44,13 @@ ...@@ -44,6 +44,13 @@
/* This means the buffer contains a list of buffer descriptors. */ /* This means the buffer contains a list of buffer descriptors. */
#define VRING_DESC_F_INDIRECT 4 #define VRING_DESC_F_INDIRECT 4
/*
* Mark a descriptor as available or used in packed ring.
* Notice: they are defined as shifts instead of shifted values.
*/
#define VRING_PACKED_DESC_F_AVAIL 7
#define VRING_PACKED_DESC_F_USED 15
/* The Host uses this in used->flags to advise the Guest: don't kick me when /* The Host uses this in used->flags to advise the Guest: don't kick me when
* you add a buffer. It's unreliable, so it's simply an optimization. Guest * you add a buffer. It's unreliable, so it's simply an optimization. Guest
* will still kick if it's out of buffers. */ * will still kick if it's out of buffers. */
...@@ -53,6 +60,23 @@ ...@@ -53,6 +60,23 @@
* optimization. */ * optimization. */
#define VRING_AVAIL_F_NO_INTERRUPT 1 #define VRING_AVAIL_F_NO_INTERRUPT 1
/* Enable events in packed ring. */
#define VRING_PACKED_EVENT_FLAG_ENABLE 0x0
/* Disable events in packed ring. */
#define VRING_PACKED_EVENT_FLAG_DISABLE 0x1
/*
* Enable events for a specific descriptor in packed ring.
* (as specified by Descriptor Ring Change Event Offset/Wrap Counter).
* Only valid if VIRTIO_RING_F_EVENT_IDX has been negotiated.
*/
#define VRING_PACKED_EVENT_FLAG_DESC 0x2
/*
* Wrap counter bit shift in event suppression structure
* of packed ring.
*/
#define VRING_PACKED_EVENT_F_WRAP_CTR 15
/* We support indirect buffer descriptors */ /* We support indirect buffer descriptors */
#define VIRTIO_RING_F_INDIRECT_DESC 28 #define VIRTIO_RING_F_INDIRECT_DESC 28
...@@ -171,4 +195,32 @@ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old) ...@@ -171,4 +195,32 @@ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old); return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
} }
struct vring_packed_desc_event {
/* Descriptor Ring Change Event Offset/Wrap Counter. */
__le16 off_wrap;
/* Descriptor Ring Change Event Flags. */
__le16 flags;
};
struct vring_packed_desc {
/* Buffer Address. */
__le64 addr;
/* Buffer Length. */
__le32 len;
/* Buffer ID. */
__le16 id;
/* The flags depending on descriptor type. */
__le16 flags;
};
struct vring_packed {
unsigned int num;
struct vring_packed_desc *desc;
struct vring_packed_desc_event *driver;
struct vring_packed_desc_event *device;
};
#endif /* _UAPI_LINUX_VIRTIO_RING_H */ #endif /* _UAPI_LINUX_VIRTIO_RING_H */
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment